RegulaTOR: A Powerful Website Fingerprinting Defense

Website Fingerprinting (WF) attacks are used by passive, local attackers to determine the destination of encrypted internet traffic by comparing the sequences of packets sent to and received by the user to a previously recorded data set. As a result, WF attacks are of particular concern to privacy-enhancing technologies such as Tor. In response, a variety of WF defenses have been developed, though they tend to incur a high bandwidth and latency overhead or require additional infrastructure, making them difficult to implement in practice. Some lighter-weight defenses have been presented as well; still, they attain only moderate effectiveness against recently published WF attacks. In this paper, we aim to present a realistic and novel defense, Regulator, that demonstrates improved overhead and high effectiveness against current WF attacks. In the closed-world setting, this defense reduces the accuracy of the state-of-the-art attack, Tik-Tok, against lightweight defenses from 66% to 22.9%. To achieve this performance, it requires minimal added latency and a bandwidth overhead 38.1% less than the leading lightweight defense. In the open-world setting, Regulator limits a precision-tuned Tik-Tok attack to an F-score of .087, compared to .625 for the best comparable lightweight defense.